Reviewer's comment Hello, my name is Sveta Nosova and I am going to review this project. Before we start, I want to pay your attention to the color marking:
Reviewer's comment Great solutions and ideas that can and should be used in the future are in green comments.
Reviewer's comment Yellow color indicates what should be optimized. This is not necessary, but it will be great if you make changes to this project.
Reviewer's comment Issues that need to be corrected to get right results are indicated in red comments. Note that the project cannot be accepted until these issues are resolved.

Please, use some color other than those listed to highlight answers to my comments. I would also ask you not to change, move or delete my comments so that it would be easier for me to navigate during the next review.

In addition, my comments are defined as headings. They can mess up the content, however, they are convenient, since you can immediately go to them. I will remove the headings from my comments in the next review.


**A few words about the project:** you did a great job, everything is clear and neat, there are analysis and intermediate conclusions. The project has a lot of graphs, which is great. I still have some questions that I've written in my comments. I've also left there some recommendations for improving the project. If you hava any questions, feel free to ask me.


**About the presentation:**

</div>

Student's comment: Hi Sveta, Thank you for you reviewing my project. I want to be a good coder, so I appreaciate your feedback! I've made updates below. Thank you, Jolene G.
Reviewer's comment 2 Jolene, thank you for sending the corrected version of the project. You've done a fantastic job 😊 I've left a few comments titled as **Reviewer's comment 2**. I've also removed the headings from the old comments. Hope, my comments were helpful. Your project has passed code review. Congratulations 😊 Take care and good luck!
Best regards, Sveta

Telling a Story with Data Course Project

Project Description

You’ve decided to open a small robot-run cafe in Los Angeles. The project is promising but expensive, so you and your partners decide to try to attract investors. They’re interested in the current market conditions — will you be able to maintain your success when the novelty of robot waiters wears off?

Tasks

Instructions for completing the project

Step 1. Download the data and prepare it for analysis

Step 2. Data analysis: Perform the following tasks:

Draw Conclusions

Data Description

Plan of Action

  1. Import Libraries
  2. Open the data files and study the general information (original dataframe)
  3. Data Preprocessing (working dataframe)
    • Create working versions of the dataframes
    • Clean up the data
  4. Analyze the data
    • Answer the requested information
  5. Draw conclusions
  6. Prepare a presentation
Reviewer's comment There's an introduction, which is good. It is important to write an introductory part, because it gives an idea about the content of the project.

1. Import Libraries

2. Open the data files and study the general information (original dataframe)

Read data as a dataframe and examine original data

Examine original df

2 Conclusion of original dataframe and general information

Actions performed

Dataframe info

Reviewer's comment Nice intro.

3 Data Preprocessing

Clean up the data and process where necessary

Plan of Action

Due to the low numbers

Save working version of the data

Fill null values

Optimize datatype storage

Retitle columns to be more readable/user friendly

Identify missing values in the dataset

Identify duplicate values in the dataset

Reviewer's comment You are absolutely right. Another option is to exclude the **id** column and look for full duplicates again. Even if you are not going to delete them, it is important to understand what we are working with
Student's comment: This is a good idea, I will evaluate necessary data better in the future

3 Conclusion: Data Preprocessing

Actions Performed

Reviewer's comment Very good. Now we can move on to the next step.

4 Analyse the Data

4.1 Investigate the proportions of the various types of establishments. Plot a graph.

Reviewer's comment Please, don't forget to sort values :)

Reviewer's comment 2

😊
Student's comment: The graph is sorted

4.1 CONCLUSION: Investigate the proportions of the various types of establishments. Plot a graph.

Reviewer's comment Great visualization!
Reviewer's comment Why, do you think, restaurants are more common? Please, try to explain it.
Student's comment: Restaurants may be the most popular because patrons wish to have a dining experience that lasts a bit longer than what the other types offer

Reviewer's comment 2

Interesting. To be honest, I don't know why restaurants are more common there. Maybe the point is, LA is a very expensive place to live. One of the most expensive in the USA. And restaurant is usually the most expensive establishment. On the other hand, cafes are a type of restaurant. Although, it cannot clearly define the difference and explain the distribution, I suppose, we can say that restaurants more often provide *food for soul* 😊 While cafe is more often just a place to drink coffee and eat something when you are hungry.

4.2 Investigate the proportions of chain and nonchain establishments. Plot a graph.

4.2 CONCLUSION: Investigate the proportions of chain and nonchain establishments. Plot a graph.

Reviewer's comment Do you have any suggestions about this result?
Student's comment: There may be more non-chain establishments because the city has rules against the number or chains in the city limits, the patrons of the city prefer local and/or unique food establishments, or maybe there are incentives given to non-chain or small businesses, so there are more of them.

Reviewer's comment 2

Yes, it's not so easily to own an establishment chain in such city.

4.3 Which type of establishment is typically a chain?

Reviewer's comment Very nice code and graph 👍 The same table can be displayed with a groupby method. Similar to the task about loans, I will use zeros and ones so that the sum is equal to the sum of ones or the number of chain establishments. And count will return the total number of elements in the group. Then the share of chain elements will be calculated as the sum divided by the number. And this is just the average. So I can create this table with just one grouping:
Reviewer's comment It is better to define the legend by ourselves using understandable words like *not chain* and *chain* instead of *false* and *true*.
Student's comment: Thank you for this code example! I am still getting used to know when it is best to use lambda functions. This is much more elegant!

Reviewer's comment 2

Take a look at this [article](https://towardsdatascience.com/lambda-functions-with-practical-examples-in-python-45934f3653a8).

4.3 CONCLUSION: Which type of establishment is typically a chain?

Reviewer's comment Interesting. All bakeries are chain establishments.
Reviewer's comment Please, add some explanations. One of the main tasks of any analyst is to explain the results.
Student's comment: The data suggests that establishments that are catering to a grab and go type of patron (bakeries, cafes, fast food) tend to be chains. This could be because they already have a solid business model and are less of a risk to fund vs independent sites. Establishments that encourage more of a sit and stay dining experience tend to be non-chains. For the same reasons listed above as to why there are more non-chains vs chains: - There may be more non-chain establishments because the city has rules against the number or chains in the city limits - the patrons of the city prefer local and/or unique food establishments - maybe there are incentives given to non-chain or small businesses, so there are more of them - They may also be less risky to fund

Reviewer's comment 2

Good :)

4.4 What characterizes chains: many establishments with a small number of seats or a few establishments with a lot of seats?

4.4 CONCLUSION: What characterizes chains: many establishments with a small number of seats or a few establishments with a lot of seats?

Reviewer's comment Yes. A quarter of establishments have no more than 13 seats.

4.5 Determine the average number of seats for each type of restaurant. On average, which type of restaurant has the greatest number of seats? Plot graphs.

Reviewer's comment Great barplot, but again, we should remember about sorting :)
Student's comment: The graph is sorted

4.5 CONCLUSION: Determine the average number of seats for each type of restaurant. On average, which type of restaurant has the greatest number of seats? Plot graphs.

4.6 Put the data on street names from the address column in a separate column.

4.7 Plot a graph of the top ten streets by number of restaurants.

Reviewer's comment You can make it hotizontal so it's easy to read names. Or, for example, you can rotate the labels on the X axis with the `plt.xticks(rotation = )` parameter.
Student's comment: The graph is sorted

4.7 CONCLUSION: Plot a graph of the top ten streets by number of restaurants.

Reviewer's comment I suppose, these streets are big and crowded.

4.8 Find the number of streets that only have one restaurant.

4.8 CONCLUSION: Find the number of streets that only have one restaurant.

4.9 For streets with a lot of restaurants, look at the distribution of the number of seats. What trends can you see?

4.9 CONCLUSION: For streets with a lot of restaurants, look at the distribution of the number of seats. What trends can you see?

Reviewer's comment Quite obvious result :) Seems like we have the same conclusion about the distributioon.
Reviewer's comment What else can we do here? We can look at the average number of seats for each establishment on these top-10 streets.
Student's comment: Calculated the average # of seats the average number of seats on the top 10 streets is 47. This is higher than the cafe average of 25 for the whole data set. However the median is 29, which is much lower suggesting that the data is right skewed, i.e. there are large outliers. i also looked at the cafe only data for the top 10 streets, see: Extra research: How many cafes are there on each of the top 10 streets? The average and median number of seats for cafes only on the top 10 streets is 22. Because these values are the same, the data is not skewed.

Extra research: What is the proportion of establishment types on the top 10 streets?

Reviewer's comment Good question.

Conclusion

Reviewer's comment I think there's an expensive rent there. What do you think?
Student's comment: Because these streets have other establishments and many have high attraction areas, it is likley that the rent is high. But it also suggests that they do quite well financially if they can maintain that location.

Extra research: What are the proportions of chain and non-chain establishments on the top 10 streets?

Conclusion

Extra research: How many cafes are there on each of the top 10 streets?

Conclusion

Reviewer's comment Great.

General Conclusion & Recommendations

General Conclusions

Overall

Recommendations

Reviewer's comment Totally agree with you.

Presentation Link - PDF

Presentation: https://drive.google.com/file/d/1pDOHgxA-n9iJ1utBtT-p7JtMx6lBUhUT/view?usp=sharing

Overall conclusion

You've done a really good job! - You've shown great presentation and coding skills. - The data was prepared successfully. - There are a lot graphs. It is good, visualization never hurts. - Moreover, the project has a great conclusion, which is also important.
Please, add some explanations for each result. It's one of the most important parts of any research. As soon as you fix it I will accept the project 😉
Student's comment: I've added comments where you requests and updated at the comments. I hope this is what you were looking for. Thank you!